Update app.py

app.py

@@ -1,12 +1,18 @@
 import gradio as gr
-from transformers import pipeline
+import torchaudio
+from speechbrain.pretrained import EncoderClassifier
 
-# Load the model separately
-model = pipeline("automatic-speech-recognition", model="speechbrain/mtl-mimic-voicebank")
+# Load the SpeechBrain model separately
+model = EncoderClassifier.from_hparams(source="speechbrain/mtl-mimic-voicebank", savedir="tmp")
 
-# Define a function to make predictions using the loaded model
+# Define the function to transcribe audio
 def transcribe(audio):
-    return model(audio)["text"]
+    # Load and process the audio file using torchaudio
+    signal, rate = torchaudio.load(audio)
+    
+    # Make predictions using the SpeechBrain model
+    output = model.classify_batch(signal)
+    return output
 
 # Define a CSS string to hide the footer
 custom_css = """